Local and non-local dependency learning and emergence of rule-like representations in speech data by deep convolutional generative adversarial networks. (January 2022)

• Record Type: Journal Article
• Authors: Beguš, Gašper
• Is Part Of: Computer speech & language. Volume 71(2022)
• Publication Date: 2022-01
• Subjects: Neural networks -- Behavioral experiments -- Machine learning -- Learning biases -- Speech -- Morphology; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101244
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: GANs discretize continuous speech data into reduced representations that resemble rule- like generalizations. We can actively observe the network's progress in learning by keeping latent space constant across different training steps. GANs provide useful information for computational models of speech even if trained on a comparatively small dataset. Local processes are easier to learn than non-local processes, which matches both behavioral data in human subjects and typology in the world's languages. Rule-like generalizations in the training data are represented as an interaction between variables in the network's latent space. Abstract: This paper argues that training Generative Adversarial Networks (GANs) on local and non-local dependencies in speech data offers insights into how deep neural networks discretize continuous data and how symbolic-like rule-based morphophonological processes emerge in a deep convolutional architecture. Acquisition of speech has recently been modeled as a dependency between latent space and data generated by GANs in Beguš (2020b), who models learning of a simple local allophonic distribution. We extend this approach to test learning of local and non-local phonological processes that include approximations of morphological processes. We further parallel outputs of the model to results of a behavioral experiment where human subjects are trained on the data used for training the GAN network. Four main conclusions emerge: (i) the networks provide useful information for computational models of speech acquisition even if trained on a comparatively small dataset of an artificial grammar learning experiment; (ii) local processes are easier to learn than non-local processes, which matches both behavioral data in human subjects and typology in the world's languages. This paper also proposes (iii) how we can actively observe the network's progress in learning and explore the effect of training steps on learning representations by keeping latent space constant across different training steps. Finally, this paper shows that (iv) the network learns to encode the presence of a prefix with a single latent variable; by interpolating this variable, we can actively observe the operation of a non-local phonological process. The proposed technique for retrieving learning representations has general implications for our understanding of how GANs discretize continuous speech data and suggests that rule-like generalizations in the training data are represented as an interaction between variables in the network's latent space.